How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
positiveabhiillms.txtpositiveabhii/kiss-the-pdf/llms.txt
KissThePDF > A free, open-source, privacy-first PDF toolkit that runs in-browser without uploads or signup. ## Main - [KissThePDF — Free, Open-Source, Privacy-First PDF Toolkit](https://www.kissthepdf.space/): Free
psinglapllms.txtpsinglap/websearch-api-eval/llms.txt
github.com/psinglap/websearch-api-eval/blob/main/eval/METRICS.md) - [Answer keys](https://github.com/psinglap/websearch-api-eval/blob/main/eval/answer_keys.csv) and [grading rubric](https://github.com/psinglap/websearch-api-eval/blob/main/eval/grading/RUBRIC.md) ## Optional - [PDF: full evaluation](https://psinglap.github.io/websearch-api-eval/pdf/web-search-api-evaluation.pdf) - [PDF: GTM memo](https://psinglap.github.io/websearch-api-eval/pdf/gtm-memo.pdf)
QuarktexReads credentialsllms.txtQuarktex/qcobrain/llms-full.txt
# qcobrain — full documentation (concatenated for one-shot LLM ingestion) # The curated index is llms.txt
sami-hussain-devllms.txtsami-hussain-dev/safe-ai-coding/llms.txt
mistakes, reviews every change from an AI and a human perspective, and produces a PDF report of what was wrong and what was fixed when the user asks. Created
sandraschiReads credentialsllms.txtsandraschi/arxiv-mcp/llms-full.txt
resolution:** `resolve_doi` (metadata + OA status via Unpaywall + Crossref), `fetch_doi_content` (downloads OA PDF, extracts text via pypdf, optionally ingests to depot). **Sampling (host must support MCP sampling):** `arxiv
sandraschillms.txtsandraschi/arxiv-mcp/llms.txt
snippets. ## DOI resolution - `resolve_doi` / `fetch_doi_content` — Unpaywall (primary) + Crossref (fallback). Extracts OA PDF, downloads and extracts text via pypdf. No API keys required
Scorpio-meowReads credentialsllms.txtScorpio-meow/AskMiao/llms.txt
對話檔案工具（列出、讀取、建立、修改另存新版本、刪除）的定義與執行；只在有對話 id 時提供，刪除一律要核准 - [backend/app/services/file_preview.py](backend/app/services/file_preview.py): 對話檔案與知識庫文件的預覽（PDF 逐頁轉圖、Word／Excel／PowerPoint 轉成結構化 JSON）；網頁檔以短效權杖在 `sandbox allow-scripts` 的 CSP 下開啟 - [backend/app/services/conversation_files.py](backend/app/services/conversation_files.py
Shangri-la-0428llms.txtShangri-la-0428/oasyce-chain/docs/llms.txt
access the data. Key env vars: `WATCH_DIRS` (required), `ALLOWED_EXTENSIONS` (e.g. `.csv,.json,.pdf`), `DEFAULT_TAGS`, `MAX_RISK_LEVEL` (`safe` or `low`), `SERVICE_URL_TEMPLATE`. ### 4f. Sell shares back
theluckystrikellms.txttheluckystrike/claude-skills-guide/llms.txt
server, npm package, tool name and buy link - [Invoice MCP server](https://claudecodeguides.com/mcp/invoice/) - [PDF MCP server](https://claudecodeguides.com/mcp/pdf/) - [Spreadsheet MCP server](https://claudecodeguides.com/mcp/spreadsheet/) - [Bank statement MCP server
Aayush-Joshi-01Reads credentialsllms.txtAayush-Joshi-01/deepcrew-ai/pages/llms-full.txt
types a given consumer sees (`chat()`, `standard()`, `verbose()`, custom). ## Latest additions Multimodal input (`image()`, `pdf()`, `user_message()`), selectable streaming visibility (`StreamPolicy`), an optional FastAPI SSE integration, structured output (`response_model
Aayush-Joshi-01llms.txtAayush-Joshi-01/deepcrew-ai/pages/llms.txt
automatic similarity + recency recall before each new run. - [Multimodal Input](https://deepcrew-ai.aayushjoshi.dev/md/guides/multimodal.md): `image()`, `pdf()`, `user_message()` content blocks. - [StreamPolicy](https://deepcrew-ai.aayushjoshi.dev/md/guides/streampolicy.md): chat / standard / verbose presets controlling which events
ArkanjiPipes a download into a shellllms.txtArkanji/iwork-studio/llms.txt
find, undo and the kit list always load. - **Every format via the app** — export (PDF, xlsx, csv, docx, epub, txt, rtf, pptx, slide images, movie; optional password), checked
Ayithamsetty-Vamsi-krishnallms.txtAyithamsetty-Vamsi-krishna/claude-skills/llms.txt
Version: 4.3.1 - License: MIT ## PRD → Complete App Pipeline Upload your Business PRD + Technical PRD (PDF, DOCX, or MD format). Say "build from PRD". 1. saas-dev-orchestrator reads both PRDs
bvolpatollms.txtbvolpato/vizmatic/docs/llms-full.txt
# Prompt # Vizmatic agent prompt Use Vizmatic to explain things visually from code. It makes
chhudsonReads credentialsllms.txtchhudson/bmad-claude-skills/docs/llms-full.txt
# BMAD Skills for Claude Code - Complete Documentation > This file contains the complete BMAD Skills
geolibrerianllms.txtgeolibrerian/gismap/llms-full.txt
printable map, poster or Smart Map Image | [print-map](https://gismap.online/agent-recipes/print-map/) | Branded PDF or Smart Image | | Make the map feel like Halloween in California | [vibe-map](https://gismap.online/skills/#recipe-vibe-map)
geolibrerianllms.txtgeolibrerian/gismap/llms.txt
printable map, poster or Smart Map Image | [print-map](https://gismap.online/agent-recipes/print-map/) | Branded PDF or Smart Image | | Make the map feel like Halloween in California | [vibe-map](https://gismap.online/skills/#recipe-vibe-map)
illodevPipes a download into a shellllms.txtillodev/workfile/site/llms-full.txt
# Workfile > You are probably an agent. Someone sent you to find out whether Workfile
LARIkozllms.txtLARIkoz/ai-model-benchmarks/llms-full.txt
architecture review | | Gemini CLI (gemini-2.5-pro) | Google | FREE | 2M | — | 0 | 0 | — | Research free, PDF analysis, visual QA, 2M context | | Llama 3.3 70B Q4 | Meta | FREE | 131K | — | 0 | 0 | — | Local
moxnollms.txtmoxno/privacyscrubber-mcp/llms.txt
files, CSV, JSON, markdown, text logs, and Microsoft Word (`.docx`) documents. - Binary formats (like PDF, ZIP) are automatically rejected with a redirection notice to prevent corrupting inputs. - Inputs: - `filePath` (string
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
